58 citations · 168 across the 34 of their papers we have counts for
34 papers
Probabilistic Residual Learning for Online Recommendations
Wenyuan Wang, Yusong Zhao, Zihao Xu +11
Modern recommender systems are typically based on deep learning (DL) models, where a dense encoder learns representations of users and items. As a result, these systems often suffe…
EditLord: Learning Code Transformation Rules for Code Editing
Weichen Li, Albert Jan, Baishakhi Ray +3
Code editing is a foundational task in software development, where its effectiveness depends on whether it introduces desired code property changes without changing the original co…
REVEAL: Robust Evolution of Vision-Language Models for Explainable AI-Video Detection
Qingyuan Liu, Yun-Yun Tsai, Ruijian Zha +4
The rapid advancement of AI-generated video poses challenges to digital authenticity and security. Current detection methods, often trained on specific datasets, struggle with the…
Diversity Helps Jailbreak Large Language Models
Weiliang Zhao, Daniel Ben-Levi, Wei Hao +2
We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generat…
I Can Hear You: Selective Robust Training for Deepfake Audio Detection
Zirui Zhang, Wei Hao, Aroon Sankoh +4
Recent advances in AI-generated voices have intensified the challenge of detecting deepfake audio, posing risks for scams and the spread of disinformation. To tackle this issue, we…
SPIN: Self-Supervised Prompt INjection
Leon Zhou, Junfeng Yang, Chengzhi Mao
Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbr…
RAFT: Realistic Attacks to Fool Text Detectors
James Wang, Ran Li, Junfeng Yang +1
Large language models (LLMs) have exhibited remarkable fluency across various tasks. However, their unethical applications, such as disseminating disinformation, have become a grow…
Learning to Rewrite: Generalized LLM-Generated Text Detection
Ran Li, Wei Hao, Weiliang Zhao +2
Large language models (LLMs) present significant risks when used to generate non-factual content and spread disinformation at scale. Detecting such LLM-generated content is crucial…
Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos
Qingyuan Liu, Pengyuan Shi, Yun-Yun Tsai +2
The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works to combat De…
SelfIE: Self-Interpretation of Large Language Model Embeddings
Haozhe Chen, Carl Vondrick, Chengzhi Mao
How do large language models (LLMs) obtain their answers? The ability to explain and control an LLM's reasoning process is key for reliability, transparency, and future model devel…
Raidar: geneRative AI Detection viA Rewriting
Chengzhi Mao, Carl Vondrick, Hao Wang +1
We find that large language models (LLMs) are more likely to modify human-written text than AI-generated text when tasked with rewriting. This tendency arises because LLMs often pe…
Robustifying Language Models with Test-Time Adaptation
Noah Thomas McDermott, Junfeng Yang, Chengzhi Mao
Large-scale language models achieved state-of-the-art performance over a number of language tasks. However, they fail on adversarial language examples, which are sentences optimize…
Interpreting and Controlling Vision Foundation Models via Text Explanations
Haozhe Chen, Junfeng Yang, Carl Vondrick +1
Large-scale pre-trained vision foundation models, such as CLIP, have become de facto backbones for various vision tasks. However, due to their black-box nature, understanding the u…
Towards Causal Deep Learning for Vulnerability Detection
Md Mahbubur Rahman, Ira Ceka, Chengzhi Mao +3
Deep learning vulnerability detection has shown promising results in recent years. However, an important challenge that still blocks it from being very useful in practice is that t…
Monitoring and Adapting ML Models on Mobile Devices
Wei Hao, Zixi Wang, Lauren Hong +5
ML models are increasingly being pushed to mobile devices, for low-latency inference and offline operation. However, once the models are deployed, it is hard for ML operators to tr…
Test-time Detection and Repair of Adversarial Samples via Masked Autoencoder
Yun-Yun Tsai, Ju-Chin Chao, Albert Wen +4
Training-time defenses, known as adversarial training, incur high training costs and do not generalize to unseen attacks. Test-time defenses solve these issues but most existing te…
Convolutional Visual Prompt for Robust Visual Perception
Yun-Yun Tsai, Chengzhi Mao, Junfeng Yang
Vision models are often vulnerable to out-of-distribution (OOD) samples without adapting. While visual prompts offer a lightweight method of input-space adaptation for large-scale…
Adversarially Robust Video Perception by Seeing Motion
Lingyu Zhang, Chengzhi Mao, Junfeng Yang +1
Despite their excellent performance, state-of-the-art computer vision models often fail when they encounter adversarial examples. Video perception models tend to be more fragile un…
Understanding Zero-Shot Adversarial Robustness for Large-Scale Models
Chengzhi Mao, Scott Geng, Junfeng Yang +2
Pretrained large-scale vision-language models like CLIP have exhibited strong generalization over unseen tasks. Yet imperceptible adversarial perturbations can significantly reduce…
Doubly Right Object Recognition: A Why Prompt for Visual Rationales
Chengzhi Mao, Revant Teotia, Amrutha Sundar +4
Many visual recognition models are evaluated only on their classification accuracy, a metric for which they obtain strong performance. In this paper, we investigate whether compute…
Robust Perception through Equivariance
Chengzhi Mao, Lingyu Zhang, Abhishek Joshi +3
Deep networks for computer vision are not reliable when they encounter adversarial examples. In this paper, we introduce a framework that uses the dense intrinsic constraints in na…
Shadows Shed Light on 3D Objects
Ruoshi Liu, Sachit Menon, Chengzhi Mao +3
3D reconstruction is a fundamental problem in computer vision, and the task is especially challenging when the object to reconstruct is partially or fully occluded. We introduce a…
Causal Transportability for Visual Recognition
Chengzhi Mao, Kevin Xia, James Wang +4
Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features. Our main observation is that image classifiers may perform poo…
A Tale of Two Models: Constructing Evasive Attacks on Edge Models
Wei Hao, Aahil Awatramani, Jiayang Hu +5
Full-precision deep learning models are typically too large or costly to deploy on edge devices. To accommodate to the limited hardware resources, models are adapted to the edge us…